What You Should Know:
- Hip disorders, comprising some of the world’s most common joint diseases, are especially prevalent among adolescents and young adults, causing stiffness, pain or a limp. But they can be hard to diagnose using solely 2D medical imaging.
- Helping to treat these disorders, the Boston Children’s Hospital’s (BCH’s) Adolescent and Young Adult Hip Preservation Program is the U.S.’s first to deploy a fully automated AI tool across its clinic.
Revolutionizing Hip Diagnosis and Treatment: VirtualHip – A Cutting-Edge Integration of 3D Imaging and Rapid Analysis for Enhanced Clinical Precision
A group of 10 researchers, supported in part by an NVIDIA Academic Hardware Grant, is collaborating on a project that involves engineers, computer scientists, orthopedic surgeons, radiologists, and software developers.
In many cases, clinicians face the challenge of devising a treatment plan based on 2D medical images, such as X-rays, CT scans, or MRIs. These plans can range from physical therapy to total hip replacement. The automatic generation of 3D models from these images, utilized for comprehensive joint assessments, can significantly enhance diagnostic accuracy, thereby informing more effective treatment strategies.
Addressing this need, VirtualHip has been fully integrated with BCH’s hip clinic and radiology database. This innovative software tool allows clinicians to access a web-based portal, where they can view and interact with 3D simulations derived from 2D medical images. They can also submit analysis requests and receive results within an hour—a process four times quicker, on average, than waiting for a radiology report after imaging. Notably, VirtualHip produces 3D models with a margin of error less than one millimeter, enabling the assessment of morphological abnormalities and the identification of issues related to hip motion, such as pain arising from hip bones rubbing against each other.
The development of VirtualHip drew upon a vast database comprising tens of millions of clinical notes and imaging data from patients seen at BCH over the last two decades. Leveraging natural language processing models and computer vision algorithms, Dr. Kiapour’s team meticulously processed this data, training the tool to differentiate between normal and pathologic hip development while identifying factors influencing hip-related issues.
“Using AI, clinicians can get more value out of the clinical data they routinely collect,” said Dr. Ata Kiapour, the lab’s principal investigator, director of the musculoskeletal informatics group at BCH and assistant professor of orthopedic surgery at Harvard Medical School. “This tool can augment their performance to make better choices in diagnosis and treatment, and free their time to focus on giving patients the best care.”
